split_pdfs.py

from os import path
from glob import glob  
from tqdm import tqdm
import time
from pyPdf import PdfFileWriter, PdfFileReader

def find_ext(dr, ext):
  return glob(path.join(dr,"*.{}".format(ext)))
  
files = find_ext("pdfs","pdf")

def split(pdfs):
  for item in tqdm(pdfs):
    inputpdf = PdfFileReader(open(item, "rb"))
    stem = item.replace("pdfs/","").replace(".pdf", "")

    for i in xrange(inputpdf.numPages):
        output = PdfFileWriter()
        output.addPage(inputpdf.getPage(i))
        outpath = "split-pdfs/" + stem + "-p" + str(i) + ".pdf"
        with open(outpath, "wb") as outputStream:
            output.write(outputStream)
        
    time.sleep(.1)

tesseract.sh

TXT_DIR="texts"

if [ ! -d "${TXT_DIR}" ];
then
  mkdir ${TXT_DIR}
fi

for TIF in *.tif; do
  TXT_NAME=$(basename ${TIF} .tif)
  TXT_FILE="${TXT_NAME}.txt"
  tesseract ${TIF} ${TXT_NAME}
  mv ${TXT_FILE} ${TXT_DIR}
  echo "Converted ${TXT_NAME}"
done

mv ${TXT_DIR} ..

tif.sh

TIF_DIR="tif"

if [ ! -d "${TIF_DIR}" ];
then
  mkdir ${TIF_DIR}
fi

for PAGE in *.pdf; do
  TIF_NAME=$(basename ${PAGE} .pdf).tif
  gs -q -dNOPAUSE -sDEVICE=tiffg4 -sOutputFile=${TIF_NAME} ${PAGE} -c quit
  mv ${TIF_NAME} ${TIF_DIR}
  echo "Converted ${TIF_NAME}"
done

mv ${TIF_DIR} ..